vuln-patch-cwe-guesser-model-microsoft-graphcodebert-base

This model is a fine-tuned version of microsoft/graphcodebert-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.8276
• Accuracy: 0.35
• F1: 0.1264

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 40
• eval_batch_size: 40
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	1	5.1591	0.0	0.0
No log	2.0	2	5.0441	0.3	0.0985
No log	3.0	3	4.9430	0.45	0.1833
No log	4.0	4	4.8677	0.35	0.1264
No log	5.0	5	4.8276	0.35	0.1264

Framework versions

• Transformers 4.55.0
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2